Carlos Quintero
Papers
14
Total Citations
139
H-Index
6
About
Carlos Quintero is a robotics researcher whose work spans motion planning, human-robot interaction, and robot learning, with particular emphasis on enabling robots to operate safely and efficiently in complex, real-world environments. He is perhaps best known for developing **MotionBenchMaker** (2021, 51 citations), a widely adopted tool that standardizes the generation and benchmarking of motion planning datasets, addressing a longstanding gap in rigorous planner evaluation. His research on experience-driven sampling distributions for high-dimensional robots (2020, 31 citations) demonstrated how local 3D workspace decompositions can dramatically improve planning efficiency by leveraging prior solutions. Quintero has also made meaningful contributions to planning under uncertainty, developing optimization-based and neural implicit approaches that scale to high-degree-of-freedom manipulators in unstructured, perceptually limited settings. His earlier work explored multimodal human-robot interaction, combining machine learning techniques to recognize emotion and interpret instructions from combined sensory signals. More recently, he has tackled partially observable environments and integrated grasp and placement reasoning into task-and-motion planning pipelines. Across his career, Quintero's research consistently bridges theoretical rigor with practical robot deployment, making him a noteworthy contributor to the modern motion planning and human-robot interaction communities.
Research Focus
Key Achievements
Top Papers
- 1MotionBenchMaker: A Tool to Generate and Benchmark Motion Planning Datasets51 citations · 2021
- 2
- 3Fast Path Planning Algorithm for the RoboCup Small Size League10 citations · 2015
- 4
- 5
- 6
- 7Human-Guided Motion Planning in Partially Observable Environments6 citations · 2022
- 8
- 9
- 10Optimal Grasps and Placements for Task and Motion Planning in Clutter3 citations · 2023